Prem K Kalra is a professor in Department of Computer Science
and Engineering at Indian Institute of Technology Delhi. He
joined IIT Delhi in Dec 1997. Earlier to that he worked at
University of Geneva, Switzerland (1994-1997). He has also
been a Visiting Faculty to Dayalbagh Educational Institute,
Agra, University of Geneva, Swiss Federal Institute of Technology
Lausanne (EPFL), Switzerland, Max-Planck Institute, Germany,
and University of Texas Austin, USA. He did his PhD in Computer
Science from Swiss Federal Institute of Technology Lausanne
(EPFL), Switzerland in 1993, MS (Computer Science) from University
of New Brunswick, Canada in 1988, MTech (Industrial Engg)
from IIT Delhi in 1985 and BSc Engineering (Mechanical Engg)
from Dayalbagh Educational Institute, Agra in 1983. His research
interests are in Computer Graphics and Animation, Visual Computing,
Multimedia Processing, Computer Vision based Intelligent Systems.
He has published over 60 papers in reputed international journals
and conferences. He is in the editorial board of the international
journal, The Visual Computer, and has been a member of many
program committees of international conferences, e.g., ICCV,
CVPR, CGI, Eurographics Worskshops, ICVGIP. He is a member
of ACM, Computer Graphics Society and Systems Society of India.
He has been involved in many sponsored projects. He is a co-founder
of Kritikal Solutions Pvt Ltd, a start up at IIT Delhi, now
located in Noida.
|
Title: Parametric
reshaping of human figures in images and videos using 3D morphable
models
Abstract:
In this talk, an approach based on 3D morphable models to
reshape the human figure maintaining the global consistency
will be presented. The basic approach of using 3D models to
manipulate 2D images relies on techniques that arise from
confluence of computer vision and computer graphics. Typically,
a 3D morphable model is derived or statistically learnt from
an example set of 3D models. Morphable models have given impressive
results for synthesis of 3D human faces and have also offered
potential for face recognition - a still relevant problem
in computer vision. In the context of reshaping of a human
body in an image, a 3D whole-body morphable model is used
to guide the changes in single images, which are obtained
through image warping. The reshaping is parameterized such
that increasing or decreasing height or weight of human figures
can result in the semantically corresponding changes in the
model maintaining a global consistency. The approach needs
to preserve the background without distortions, which can
be obtained by separating the human figure from the background.
Reshaping of human figures in videos maintaining spatio-temporal
consistency shall also be discussed. This offers interesting
applications for photo-realistic image manipulation with human
figures and post processing applications in movies and video
productions with human actors. The talk is based on the collection
of recent research from the literature and some related work
done at the vision-graphics group in the department of computer
science and engineering at IIT Delhi.
http://www.cse.iitd.ernet.in/~pkalra/
|